Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 280
    Prev
    Next
    INDEX
    Explanations

    Actually

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الأس
    -0.08
     المع
    -0.08
     ___
    -0.07
    Prin
    -0.07
     Charlotte
    -0.07
     unk
    -0.07
    名字
    -0.07
     Kav
    -0.07
     Pfer
    -0.07
     الهو
    -0.07
    POSITIVE LOGITS
     subsets
    0.09
    valuable
    0.08
    	valid
    0.08
     gerais
    0.08
    ")]↵
    0.08
     blanket
    0.08
    нести
    0.08
     catered
    0.08
    ummary
    0.08
    oths
    0.08
    Activations Density 0.039%

    No Known Activations